Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.5045. Min Act: -0.1700
Data Index: 2256109 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4721. Min Act: -0.1700
Data Index: 2816662 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4396. Min Act: -0.1700
Data Index: 4333629 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4396. Min Act: -0.1700
Data Index: 5737360 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4559. Min Act: -0.1700
Data Index: 2345488 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4233. Min Act: -0.1700
Data Index: 7889273 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4233. Min Act: -0.1700
Data Index: 6377217 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4233. Min Act: -0.1700
Data Index: 8817330 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4233. Min Act: -0.1700
Data Index: 6472165 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4070. Min Act: -0.1700
Data Index: 3633503 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3907. Min Act: -0.1700
Data Index: 1475375 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.4233. Min Act: -0.1700
Data Index: 1161831 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3907. Min Act: -0.1700
Data Index: 16010 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3580. Min Act: -0.1700
Data Index: 3772189 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3580. Min Act: -0.1700
Data Index: 3553037 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3580. Min Act: -0.1700
Data Index: 7971003 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3744. Min Act: -0.1700
Data Index: 2527975 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3907. Min Act: -0.1700
Data Index: 1947787 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3744. Min Act: -0.1700
Data Index: 5538450 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5045. Min Range: -2.5045
Max Act: 2.3580. Min Act: -0.1700
Data Index: 6103039 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19